© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11409
    Prev
    Next
    INDEX
    Explanations

    SS, MSSQL, abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects numeric tokens, especially floating-point numbers or large multi-digit numerals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ดัง
    0.55
    стары
    0.55
    sev
    0.55
    राग
    0.54
    ución
    0.53
    怪
    0.53
    ناها
    0.53
    ząd
    0.52
    ดู
    0.52
     FRED
    0.52
    POSITIVE LOGITS
    entials
    0.80
    ENTIAL
    0.77
    entially
    0.75
    alamualaikum
    0.71
    ंका
    0.66
    uance
    0.66
    ential
    0.65
    essing
    0.65
    essment
    0.64
    s
    0.63
    Activations Density 0.397%

    No Known Activations